Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate causation or examples in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    thus introducing a conclusion or result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.39
     nakalista
    -0.38
    rawtypes
    -0.35
    outState
    -0.35
    spinner
    -0.35
    IntoConstraints
    -0.34
     slad
    -0.34
    TokenNameLBRACE
    -0.34
    jstor
    -0.34
    PhysRevD
    -0.32
    POSITIVE LOGITS
    GEBURTS
    0.63
     Offisielt
    0.55
     cherchés
    0.55
    tvguidetime
    0.54
     تانيه
    0.53
     wireType
    0.53
     مرئيه
    0.51
    utilisons
    0.50
    EndContext
    0.49
     Taktlose
    0.49
    Act Density 0.169%

    No Known Activations